English
Related papers

Related papers: Reducing the Amount of Real World Data for Object …

200 papers

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…

Computer Vision and Pattern Recognition · Computer Science 2019-02-27 Stefan Hinterstoisser , Olivier Pauly , Hauke Heibel , Martina Marek , Martin Bokeloh

Deep learning models frequently suffer from various problems such as class imbalance and lack of robustness to distribution shift. It is often difficult to find data suitable for training beyond the available benchmarks. This is especially…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Pratinav Seth , Akshat Bhandari , Kumud Lakara

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…

Computer Vision and Pattern Recognition · Computer Science 2018-11-20 Bolin Liu , Xiao Shu , Xiaolin Wu

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capability to new object classes requires large amounts of annotated training data,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Vikhyat Agarwal , Jiayi Cora Guo , Declan Hoban , Sissi Zhang , Nicholas Moran , Peter Cho , Srilakshmi Pattabiraman , Shantanu Joshi

Synthetic data has emerged as a cost-effective alternative to real data for training artificial neural networks (ANN). However, the disparity between synthetic and real data results in a domain gap. That gap leads to poor performance and…

Machine Learning · Computer Science 2025-09-03 Paul Wachter , Lukas Niehaus , Julius Schöning

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Stefan Hinterstoisser , Vincent Lepetit , Paul Wohlhart , Kurt Konolige

Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. In this work, we explore how high quality physically-based rendering and domain…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Jason W. Anderson , Marcin Ziolkowski , Ken Kennedy , Amy W. Apon

In many manufacturing settings, annotating data for machine learning and computer vision is costly, but synthetic data can be generated at significantly lower cost. Substituting the real-world data with synthetic data is therefore appealing…

Machine Learning · Computer Science 2024-06-28 Lukas Malte Kemeter , Rasmus Hvingelby , Paulina Sierak , Tobias Schön , Bishwajit Gosswam

Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vision exploit deep Convolutional Neural Networks (CNN) to…

Computer Vision and Pattern Recognition · Computer Science 2017-09-11 Georgios Georgakis , Arsalan Mousavian , Alexander C. Berg , Jana Kosecka

Field detection in team sports is an essential task in sports video analysis. However, collecting large-scale and diverse real-world datasets for training detection models is often cost and time-consuming. Synthetic datasets, which allow…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 HaoBin Qin , Jiale Fang , Keisuke Fujii

Despite the notable accomplishments of deep object detection models, a major challenge that persists is the requirement for extensive amounts of training data. The process of procuring such real-world data is a laborious undertaking, which…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Roy Voetman , Maya Aghaei , Klaas Dijkstra

This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines. While generating…

Computer Vision and Pattern Recognition · Computer Science 2019-04-30 Kai Wang , Fuyuan Shi , Wenqi Wang , Yibing Nan , Shiguo Lian

The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising…

Computer Vision and Pattern Recognition · Computer Science 2018-03-23 Nikolaus Mayer , Eddy Ilg , Philipp Fischer , Caner Hazirbas , Daniel Cremers , Alexey Dosovitskiy , Thomas Brox

This paper demonstrates how simulated images can be useful for object detection tasks in the agricultural sector, where labeled data can be scarce and costly to collect. We consider training on mixed datasets with real and simulated data…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 Sunny Goondram , Akansel Cosgun , Dana Kulic

One of the grand challenges of deep learning is the requirement to obtain large labeled training data sets. While synthesized data sets can be used to overcome this challenge, it is important that these data sets close the reality gap,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Sebastian Hartwig , Timo Ropinski

Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…

Robotics · Computer Science 2018-10-01 Jonathan Tremblay , Thang To , Balakumar Sundaralingam , Yu Xiang , Dieter Fox , Stan Birchfield

Self-training allows a network to learn from the predictions of a more complicated model, thus often requires well-trained teacher models and mixture of teacher-student data while multi-task learning jointly optimizes different targets to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Hoàng-Ân Lê , Minh-Tan Pham

The need for large annotated image datasets for training Convolutional Neural Networks (CNNs) has been a significant impediment for their adoption in computer vision applications. We show that with transfer learning an effective object…

Computer Vision and Pattern Recognition · Computer Science 2017-09-19 Param S. Rajpura , Hristo Bojinov , Ravi S. Hegde

Synthetic-to-real data translation using generative adversarial learning has achieved significant success in improving synthetic data. Yet, limited studies focus on deep evaluation and comparison of adversarial training on general-purpose…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Tingwei Shen , Ganning Zhao , Suya You

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Yue Yao , Liang Zheng , Xiaodong Yang , Milind Napthade , Tom Gedeon